LATIDIA · Robótica

HECHO: Un modelo de base de fuerza-acción-pista multimodal para la destreza de humano a robot

arXiv: 2610.19155v1Tipo de anuncio: nuevo Resumen: Las demostraciones humanas ofrecen una alternativa escalable a la costosa recopilación de datos de robots para la manipulación hábil, pero la mayoría de los conjuntos de datos humanos carecen de mediciones de fuerza. Hombre hábil

La noticia

arXiv:2610.19155v1 Announce Type: new Abstract: Human demonstrations offer a scalable alternative to costly robot data collection for dexterous manipulation, but most human datasets lack force measurements. Dexterous manipulation requires not only visual and proprioceptive understanding but also the ability to anticipate and regulate interaction forces. To scale force-aware human-robot co-training, we introduce EgoForce, a large-scale human tactile dataset capturing force-rich manipulation experience, and combine it with robot demonstrations for pretraining. We present FACT, a robot foundation model that cascades from prospective visual planning to force-aware refinement for dexterous manipulation. FACT comprises two jointly trained components. A Track-Guided Coarse Planner jointly predicts actions, future video, and visual tracks. Future video and